# As a condition of accessing this website, you agree to abide by the
# following content signals:

# (a)  If a content-signal = yes, you may collect content for the
#      corresponding use.
# (b)  If a content-signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a content signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via content signal with respect to the corresponding use.

# The content signals and their meanings are:

# search: building a search index and providing search results (e.g., returning
#         hyperlinks and short excerpts from your website's contents). Search
#         does not include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of
#           content for generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# Blanket preference under User-agent: *: search=yes, ai-input=no, ai-train=no, use=reference.
# Known training crawlers also get Disallow: / below.
# Human-readable terms: https://joshuamorris.info/content-use/
# Lighthouse's robots-txt audit does not recognize Content-signal yet; LHCI
# skips that audit so SEO can stay at 1.0 (see scripts/lighthouse/lhci-base.cjs).

# *
User-agent: *
Content-signal: search=yes, ai-input=no, ai-train=no, use=reference
Allow: /

# AI2Bot
User-agent: AI2Bot
Disallow: /

# AI2Bot-DeepResearchEval
User-agent: AI2Bot-DeepResearchEval
Disallow: /

# Ai2Bot-Dolma
User-agent: Ai2Bot-Dolma
Disallow: /

# Amazonbot
User-agent: Amazonbot
Disallow: /

# Applebot-Extended
User-agent: Applebot-Extended
Disallow: /

# Bytespider
User-agent: Bytespider
Disallow: /

# CCBot
User-agent: CCBot
Disallow: /

# ChatGLM-Spider
User-agent: ChatGLM-Spider
Disallow: /

# Claude-Web
User-agent: Claude-Web
Disallow: /

# ClaudeBot
User-agent: ClaudeBot
Disallow: /

# DeepSeekBot
User-agent: DeepSeekBot
Disallow: /

# Diffbot
User-agent: Diffbot
Disallow: /

# DoubaoBot
User-agent: DoubaoBot
Disallow: /

# FacebookBot
User-agent: FacebookBot
Disallow: /

# Google-Extended
User-agent: Google-Extended
Disallow: /

# GPTBot
User-agent: GPTBot
Disallow: /

# ICC-Crawler
User-agent: ICC-Crawler
Disallow: /

# ImagesiftBot
User-agent: ImagesiftBot
Disallow: /

# LAIONDownloader
User-agent: LAIONDownloader
Disallow: /

# Meta-ExternalAgent
User-agent: Meta-ExternalAgent
Disallow: /

# MistralAI-Training
User-agent: MistralAI-Training
Disallow: /

# Timpibot
User-agent: Timpibot
Disallow: /

# VelenPublicWebCrawler
User-agent: VelenPublicWebCrawler
Disallow: /

# Webzio-Extended
User-agent: Webzio-Extended
Disallow: /

# YaK
User-agent: YaK
Disallow: /

# YandexAdditional
User-agent: YandexAdditional
Disallow: /

# YandexAdditionalBot
User-agent: YandexAdditionalBot
Disallow: /

# anthropic-ai
User-agent: anthropic-ai
Disallow: /

# cohere-ai
User-agent: cohere-ai
Disallow: /

# cohere-training-data-crawler
User-agent: cohere-training-data-crawler
Disallow: /

# img2dataset
User-agent: img2dataset
Disallow: /

# laion-huggingface-processor
User-agent: laion-huggingface-processor
Disallow: /

# meta-externalagent
User-agent: meta-externalagent
Disallow: /

# omgili
User-agent: omgili
Disallow: /

# omgilibot
User-agent: omgilibot
Disallow: /

# webzio-extended
User-agent: webzio-extended
Disallow: /

# Host
Host: joshuamorris.info
# Sitemaps
Sitemap: https://joshuamorris.info/sitemap.xml